ARTIFICIAL INTELLIGENCE–DRIVEN ECONOMIC FORECASTING SYSTEMS: METHODOLOGICAL ADVANCES, EMPIRICAL EVIDENCE, AND POLICY IMPLICATIONS

Abstract

The rapid development of artificial intelligence (AI) has fundamentally transformed economic forecasting by enabling more accurate, adaptive, and data-driven prediction systems. Traditional econometric models, while theoretically robust, often struggle to capture the nonlinear, dynamic, and high-dimensional nature of modern economic systems. This paper explores the conceptual foundations, methodological advancements, and empirical applications of AI-powered economic forecasting systems. Drawing on recent global evidence and macroeconomic data, the study highlights the advantages of machine learning and deep learning approaches in forecasting macroeconomic indicators, financial market trends, and structural economic changes. In addition, the article provides a focused analysis of emerging economies, emphasizing Uzbekistan’s digital transformation and macroeconomic performance. Empirical data demonstrate how AI-driven forecasting models contribute to improved policy formulation, financial stability, and long-term development planning. The findings confirm that AI-based forecasting systems significantly enhance predictive accuracy, responsiveness, and decision-making quality, while also raising important challenges related to transparency, data quality, and governance.